clusterkit 0.3.0-x86_64-linux

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (59) hide show
  1. checksums.yaml +7 -0
  2. data/.rspec +3 -0
  3. data/.simplecov +47 -0
  4. data/CHANGELOG.md +35 -0
  5. data/CLAUDE.md +226 -0
  6. data/Cargo.lock +3228 -0
  7. data/Cargo.toml +8 -0
  8. data/Gemfile +17 -0
  9. data/IMPLEMENTATION_NOTES.md +143 -0
  10. data/LICENSE.txt +21 -0
  11. data/PYTHON_COMPARISON.md +183 -0
  12. data/README.md +744 -0
  13. data/Rakefile +259 -0
  14. data/docs/KNOWN_ISSUES.md +130 -0
  15. data/docs/RUST_ERROR_HANDLING.md +164 -0
  16. data/docs/TEST_FIXTURES.md +170 -0
  17. data/docs/UMAP_EXPLAINED.md +362 -0
  18. data/docs/UMAP_TROUBLESHOOTING.md +284 -0
  19. data/docs/VERBOSE_OUTPUT.md +84 -0
  20. data/docs/assets/clusterkit-wide.png +0 -0
  21. data/docs/assets/clusterkit.png +0 -0
  22. data/docs/assets/visualization.png +0 -0
  23. data/examples/hdbscan_example.rb +147 -0
  24. data/examples/optimal_kmeans_example.rb +96 -0
  25. data/examples/pca_example.rb +114 -0
  26. data/examples/reproducible_umap.rb +99 -0
  27. data/examples/verbose_control.rb +43 -0
  28. data/ext/clusterkit/Cargo.toml +26 -0
  29. data/ext/clusterkit/extconf.rb +23 -0
  30. data/ext/clusterkit/src/clustering/hdbscan_wrapper.rs +80 -0
  31. data/ext/clusterkit/src/clustering.rs +221 -0
  32. data/ext/clusterkit/src/embedder.rs +349 -0
  33. data/ext/clusterkit/src/hnsw.rs +579 -0
  34. data/ext/clusterkit/src/lib.rs +24 -0
  35. data/ext/clusterkit/src/svd.rs +89 -0
  36. data/ext/clusterkit/src/tests.rs +16 -0
  37. data/ext/clusterkit/src/utils.rs +183 -0
  38. data/lib/clusterkit/3.1/clusterkit.so +0 -0
  39. data/lib/clusterkit/3.2/clusterkit.so +0 -0
  40. data/lib/clusterkit/3.3/clusterkit.so +0 -0
  41. data/lib/clusterkit/3.4/clusterkit.so +0 -0
  42. data/lib/clusterkit/clustering/hdbscan.rb +164 -0
  43. data/lib/clusterkit/clustering.rb +194 -0
  44. data/lib/clusterkit/clusterkit.rb +14 -0
  45. data/lib/clusterkit/configuration.rb +24 -0
  46. data/lib/clusterkit/data_validator.rb +132 -0
  47. data/lib/clusterkit/dimensionality/pca.rb +251 -0
  48. data/lib/clusterkit/dimensionality/svd.rb +175 -0
  49. data/lib/clusterkit/dimensionality/umap.rb +282 -0
  50. data/lib/clusterkit/dimensionality.rb +29 -0
  51. data/lib/clusterkit/hdbscan_api_design.rb +142 -0
  52. data/lib/clusterkit/hnsw.rb +251 -0
  53. data/lib/clusterkit/preprocessing.rb +106 -0
  54. data/lib/clusterkit/silence.rb +42 -0
  55. data/lib/clusterkit/utils.rb +51 -0
  56. data/lib/clusterkit/version.rb +5 -0
  57. data/lib/clusterkit.rb +105 -0
  58. data/lib/tasks/visualize.rake +641 -0
  59. metadata +220 -0
metadata ADDED
@@ -0,0 +1,220 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: clusterkit
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.3.0
5
+ platform: x86_64-linux
6
+ authors:
7
+ - Chris Petersen
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2026-06-20 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: rb_sys
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '0.9'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '0.9'
27
+ - !ruby/object:Gem::Dependency
28
+ name: benchmark
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ">="
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ">="
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: csv
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: rake
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - "~>"
60
+ - !ruby/object:Gem::Version
61
+ version: '13.0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - "~>"
67
+ - !ruby/object:Gem::Version
68
+ version: '13.0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: rake-compiler
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - "~>"
74
+ - !ruby/object:Gem::Version
75
+ version: '1.2'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - "~>"
81
+ - !ruby/object:Gem::Version
82
+ version: '1.2'
83
+ - !ruby/object:Gem::Dependency
84
+ name: rspec
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - "~>"
88
+ - !ruby/object:Gem::Version
89
+ version: '3.0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - "~>"
95
+ - !ruby/object:Gem::Version
96
+ version: '3.0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: simplecov
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - "~>"
102
+ - !ruby/object:Gem::Version
103
+ version: '0.22'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - "~>"
109
+ - !ruby/object:Gem::Version
110
+ version: '0.22'
111
+ - !ruby/object:Gem::Dependency
112
+ name: yard
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - "~>"
116
+ - !ruby/object:Gem::Version
117
+ version: '0.9'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - "~>"
123
+ - !ruby/object:Gem::Version
124
+ version: '0.9'
125
+ description: A comprehensive clustering toolkit for Ruby, providing UMAP, PCA, K-means,
126
+ HDBSCAN and more. Built on top of annembed and hdbscan Rust crates for blazing-fast
127
+ performance.
128
+ email:
129
+ - chris@petersen.io
130
+ executables: []
131
+ extensions: []
132
+ extra_rdoc_files: []
133
+ files:
134
+ - ".rspec"
135
+ - ".simplecov"
136
+ - CHANGELOG.md
137
+ - CLAUDE.md
138
+ - Cargo.lock
139
+ - Cargo.toml
140
+ - Gemfile
141
+ - IMPLEMENTATION_NOTES.md
142
+ - LICENSE.txt
143
+ - PYTHON_COMPARISON.md
144
+ - README.md
145
+ - Rakefile
146
+ - docs/KNOWN_ISSUES.md
147
+ - docs/RUST_ERROR_HANDLING.md
148
+ - docs/TEST_FIXTURES.md
149
+ - docs/UMAP_EXPLAINED.md
150
+ - docs/UMAP_TROUBLESHOOTING.md
151
+ - docs/VERBOSE_OUTPUT.md
152
+ - docs/assets/clusterkit-wide.png
153
+ - docs/assets/clusterkit.png
154
+ - docs/assets/visualization.png
155
+ - examples/hdbscan_example.rb
156
+ - examples/optimal_kmeans_example.rb
157
+ - examples/pca_example.rb
158
+ - examples/reproducible_umap.rb
159
+ - examples/verbose_control.rb
160
+ - ext/clusterkit/Cargo.toml
161
+ - ext/clusterkit/extconf.rb
162
+ - ext/clusterkit/src/clustering.rs
163
+ - ext/clusterkit/src/clustering/hdbscan_wrapper.rs
164
+ - ext/clusterkit/src/embedder.rs
165
+ - ext/clusterkit/src/hnsw.rs
166
+ - ext/clusterkit/src/lib.rs
167
+ - ext/clusterkit/src/svd.rs
168
+ - ext/clusterkit/src/tests.rs
169
+ - ext/clusterkit/src/utils.rs
170
+ - lib/clusterkit.rb
171
+ - lib/clusterkit/3.1/clusterkit.so
172
+ - lib/clusterkit/3.2/clusterkit.so
173
+ - lib/clusterkit/3.3/clusterkit.so
174
+ - lib/clusterkit/3.4/clusterkit.so
175
+ - lib/clusterkit/clustering.rb
176
+ - lib/clusterkit/clustering/hdbscan.rb
177
+ - lib/clusterkit/clusterkit.rb
178
+ - lib/clusterkit/configuration.rb
179
+ - lib/clusterkit/data_validator.rb
180
+ - lib/clusterkit/dimensionality.rb
181
+ - lib/clusterkit/dimensionality/pca.rb
182
+ - lib/clusterkit/dimensionality/svd.rb
183
+ - lib/clusterkit/dimensionality/umap.rb
184
+ - lib/clusterkit/hdbscan_api_design.rb
185
+ - lib/clusterkit/hnsw.rb
186
+ - lib/clusterkit/preprocessing.rb
187
+ - lib/clusterkit/silence.rb
188
+ - lib/clusterkit/utils.rb
189
+ - lib/clusterkit/version.rb
190
+ - lib/tasks/visualize.rake
191
+ homepage: https://github.com/scientist-labs/clusterkit
192
+ licenses:
193
+ - MIT
194
+ metadata:
195
+ homepage_uri: https://github.com/scientist-labs/clusterkit
196
+ source_code_uri: https://github.com/scientist-labs/clusterkit
197
+ changelog_uri: https://github.com/scientist-labs/clusterkit/blob/main/CHANGELOG.md
198
+ post_install_message:
199
+ rdoc_options: []
200
+ require_paths:
201
+ - lib
202
+ required_ruby_version: !ruby/object:Gem::Requirement
203
+ requirements:
204
+ - - ">="
205
+ - !ruby/object:Gem::Version
206
+ version: '3.1'
207
+ - - "<"
208
+ - !ruby/object:Gem::Version
209
+ version: 3.5.dev
210
+ required_rubygems_version: !ruby/object:Gem::Requirement
211
+ requirements:
212
+ - - ">="
213
+ - !ruby/object:Gem::Version
214
+ version: '0'
215
+ requirements: []
216
+ rubygems_version: 3.5.23
217
+ signing_key:
218
+ specification_version: 4
219
+ summary: High-performance clustering and dimensionality reduction for Ruby
220
+ test_files: []